Abstract
This study presents a novel method for the automatic detection of debris flow motion and velocity measurement using deep learning and image processing techniques. An advanced convolutional neural network (CNN) model based on the You Only Look Once algorithm was employed to identify debris flow motion from videos recorded by a camera system. An image processing technique was also proposed to calculate the front velocity of the detected debris flow along a channel. The CNN model was trained and tested on an image dataset (named Debrisflow21) derived from 12 debris flow videos (5950 frames) that were obtained from small flume tests, large flume tests, and several debris flow events. The results showed that the debris flow detection model using CNN achieved an average precision (AP) of 96.37% and an average intersection over union of 84.80% on the test datasets. The application results of the proposed CNN model to five additional videos reached approximately 39 frames per second with an AP over 99.72%. In addition, the accuracy of the velocity calculation results tested on small flume and large flume experiment videos ranged between 87.1 and 97.3%. The proposed method exhibited high accuracy and fast processing speed; thus, it can be applied for early detection and warning systems.
This is a preview of subscription content, log in via an institution to check access.
References
Arattano M, Marchi L (2005) Measurements of debris flow velocity through cross-correlation of instrumentation data. Nat Haz Earth Syst Sci 5:137–142. https://doi.org/10.5194/nhess-5-137-2005
Arattano M, Marchi L, Cavalli M (2012) Analysis of debris-flow recordings in an instrumented basin: confirmations and new findings. NNat Haz Earth Syst Sci 12:679–686. https://doi.org/10.5194/nhess-12-679-2012
Arattano M, Marchi L (2000) Video-derived velocity distribution along a debris flow surge. Phys Chem Earth Part B 25:781–784. https://doi.org/10.1016/S1464-1909(00)00101-5
Arattano M, Marchi L (2008) Systems and sensors for debris-flow monitoring and warning. Sensors 8:2436–2452. https://doi.org/10.3390/s8042436
Berger C, McArdell BW, Schlunegger F (2011) Sediment transfer patterns at the Illgraben catchment, Switzerland: implications for the time scales of debris flow activities. Geomorphology 125:421–432. https://doi.org/10.1016/j.geomorph.2010.10.019
Bochkovskiy A, Wang C Y, Liao H Y M (2020) YOLOv4: optimal speed and accuracy of object detection. ArXiv preprint. https://arxiv.org/abs/2004.10934
Catani F (2020) Landslide detection by deep learning of non-nadiral and crowdsourced optical images. Landslides 18:1025–1044. https://doi.org/10.1007/s10346-020-01513-4
Chen H, Hu K, Cui P, Chen X (2017) Investigation of vertical velocity distribution in debris flows by PIV measurement. Geomat Nat Haz Risk 8:1631–1642. https://doi.org/10.1080/19475705.2017.1366955
Chou HT, Chang YL, Zhang SC (2013) Acoustic signals and geophone response of rainfall-induced debris flows. J Chin Inst Eng 36:335–347. https://doi.org/10.1080/02533839.2012.730269
Coviello V, Arattano M, Turconi L (2015) Detecting torrential processes from a distance with a seismic monitoring network. Nat Hazards 78:2055–2080. https://doi.org/10.1007/s11069-015-1819-2
Dailymail (2017) Spectacular avalanche rages down a Turkish ravine as stunned onlooker captures earth-shuddering force of nature from a hillside retreat. https://www.dailymail.co.uk/news/article-4446942/Spectacular-avalanche-rages-Turkish-ravine.html
Girshick R, Donahue J, Darrell T, Malik J, Berkeley UC (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. 2014 IEEE Conf Comp Vis Patt Recog 580−587. https://doi.org/10.1109/CVPR.2014.81
He K, Gkioxari G, Dollar P, Girshick R (2017) Mask R-CNN. Proceed IEEE Int Conf Comp Vis 2980−2988. https://doi.org/10.1109/ICCV.2017.322
Huang CJ, Yin HY, Chen CY, Yeh CH, Wang CL (2007) Ground vibrations produced by rock motions and debris flows. J Geophys Res Earth Surf 112:1–20. https://doi.org/10.1029/2005JF000437
Hungr O, Leroueil S, Picarelli L (2014) The Varnes classification of landslide types, an update. Landslides 11:167–194. https://doi.org/10.1007/s10346-013-0436-y
Hürlimann M, Rickenmann D, Graf C (2003) Field and monitoring data of debris-flow events in the Swiss Alps. Can Geotech J 40:161–175. https://doi.org/10.1139/t02-087
Iverson RM (1997) The physics of debris flows. Rev Geophys. https://doi.org/10.1029/97RG00426
Ji S, Yu D, Shen C, Li W, Xu Q (2020) Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks. Landslides 17:1337–1352. https://doi.org/10.1007/s10346-020-01353-2
Kogelnig A, Hübl J, Suriñach E, Vilajosana I, Zhang S, Yun N, Mcardell B W (2011) A study of infrasonic signals of debris flows. International Conference on Debris-Flow Hazards Mitigation: Mechanics, Prediction, and Assessment, pp 563–572. https://doi.org/10.4408/IJEGE.2011-03.B-062
Lin T Y, Goyal P, Girshick R, He K, Dollar P (2017) Focal loss for dense object detection. Proceed IEEE Int Conf Comp Vis 2999–3007. https://doi.org/10.1109/ICCV.2017.324
Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. Proceed IEEE Conf Comp Vis Patt Recogn 8759−8768. https://doi.org/10.1109/CVPR.2018.00913
Logan M, Iverson R M, Obryk M K (2018) Video documentation of experiments at the USGS debris-flow flume 1992–2017. https://pubs.usgs.gov/of/2007/1315/
Marchetti E, Walter F, Barfucci G, Genco R, Wenner M, Ripepe M, McArdell B, Price C (2019) Infrasound array analysis of debris flow activity and implication for early warning. J Geophys Res Earth Surf 124:567–587. https://doi.org/10.1029/2018JF004785
Marchi L, Arattano M, Deganutti AM (2002) Ten years of debris-flow monitoring in the Moscardo Torrent (Italian Alps). Geomorphology 46:1–17. https://doi.org/10.1016/S0169-555X(01)00162-3
Msonda P, Uymaz SA, Karaaǧaç S (2020) Spatial pyramid pooling in deep convolutional networks for automatic tuberculosis diagnosis. Traitement Du Signal 37:1075–1084. https://doi.org/10.18280/TS.370620
Pi Y, Nath N D, Behzadan AH (2020) Convolutional neural networks for object detection in aerial imagery for disaster response and recovery. Adv Eng Inform 43. https://doi.org/10.1016/j.aei.2019.101009
Rahnemoonfar M, Murphy R, Miquel MV, Dobbs D, Adams A (2018) Flooded area detection from UAV images based on densely connected recurrent neural networks. Int Geosci Remote Sens Sympo (IGARSS), 1788–1791. https://doi.org/10.1109/IGARSS.2018.8517946
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. Proceedings of the IEEE Comp Soc Conf Comp Vis Patt Recogn 779–788. https://doi.org/10.1109/CVPR.2016.91
Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. 2017 IEEE Conf Comp Vision and Pattern Recogn (CVPR), pp 6517–6525. https://doi.org/10.1109/CVPR.2017.690
Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. ArXiv preprint. https://arxiv.org/pdf/1804.02767.pdf
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Schimmel A, Hübl J (2016) Automatic detection of debris flows and debris floods based on a combination of infrasound and seismic signals. Landslides 13:1181–1196. https://doi.org/10.1007/s10346-015-0640-z
Theule JI, Crema S, Marchi L, Cavalli M, Comiti F (2018) Exploiting LSPIV to assess debris-flow velocities in the field. Nat Hazard 18:1–13. https://doi.org/10.5194/nhess-18-1-2018
Tzutalin (2015) LabelImg. https://github.com/tzutalin/labelImg
Uddin MS, Inaba H, Itakura Y, Yoshida Y, Kasahara M (1998) Estimation of the surface velocity of debris flow with computer-based spatial filtering. Applied Optics: Information Processing (optical Society of America) 37:6234–6239. https://doi.org/10.1364/ao.37.006234
Uddin MS, Inaba H, Itakura Y, Yoshida Y, Kasahara M (1999) Adaptive computer-based spatial filtering method for more accurate estimation of the surface velocity of debris flow. Applied Optics: Information Processing (optical Society of America) 38:6714–6721. https://doi.org/10.1364/ao.38.006714
Uddin MS, Inaba H, Itakura Y, Yoshida Y, Kasahara M (2001) Large motion estimation by gradient technique−application to debris flow velocity field. Phys Chem Earth (elsevier) 26:633–638. https://doi.org/10.1016/S1464-1917(01)00060-5
Vilajosana I, Suriñach E, Abellán A, Khazaradze G, Garcia D, Llosa J (2008) Rockfall induced seismic signals: case study in Montserrat, Catalonia. Nat Hazards Earth System Sci 8:805–812. https://doi.org/10.5194/nhess-8-805-2008
Wang C Y, Liao H Y M, Yeh I H, Wu Y H, Chen P Y, Hsieh J W (2019) CSPNET: anew backbone that can enhance learning capability of CNN. ArXiv preprint. https://arxiv.org/abs/1911.11929
Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2019) Distance-IoU loss: faster and better learning for bounding box regression. Proceedings of the AAAI Conference on Artificial Intelligence 34:12993–13000. https://doi.org/10.1609/aaai.v34i07.6999
Funding
This work was supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (grant 22TSRD- C151228- 04) and Basis Science Research Program through the National Research Foundation of Korea (NRF) funded by the Korean Ministry of Education (grant no. 2018R1D1A1B07049360).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Pham, MV., Kim, YT. Debris flow detection and velocity estimation using deep convolutional neural network and image processing. Landslides 19, 2473–2488 (2022). https://doi.org/10.1007/s10346-022-01931-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-022-01931-6